From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-2.9 required=3.0 tests=DKIM_SIGNED,DKIM_VALID, DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,SPF_PASS, T_DKIMWL_WL_HIGH,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1B6D2C4321E for ; Fri, 7 Sep 2018 21:41:27 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id BE60F2083D for ; Fri, 7 Sep 2018 21:41:26 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=amazon.de header.i=@amazon.de header.b="cLuDWGxT" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org BE60F2083D Authentication-Results: mail.kernel.org; dmarc=fail (p=quarantine dis=none) header.from=amazon.de Authentication-Results: mail.kernel.org; spf=none smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1730294AbeIHCYT (ORCPT ); Fri, 7 Sep 2018 22:24:19 -0400 Received: from smtp-fw-6001.amazon.com ([52.95.48.154]:60236 "EHLO smtp-fw-6001.amazon.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1729502AbeIHCYR (ORCPT ); Fri, 7 Sep 2018 22:24:17 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=amazon.de; i=@amazon.de; q=dns/txt; s=amazon201209; t=1536356483; x=1567892483; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=oU6+ToIHR70hf2UcDbePrNlBRyzUIVcZFSg2fyb9q90=; b=cLuDWGxTySdXa3ZToL1+KGZ+WWBGVzEhK/XI1WalXizVwvTJr9mS3/DL JWdbZ/OtRtzqVmA/Jo+mncpcNdDrn8Zgl4FzS+kUkqCkbBWKIkuK4xkEh s4N2JWS8YJmUlY6tfGUJdbD+NzESV+RF7JbxRiNfjF4R8+ZxxnFL3ssvH M=; X-IronPort-AV: E=Sophos;i="5.53,343,1531785600"; d="scan'208";a="355980785" Received: from iad6-co-svc-p1-lb1-vlan3.amazon.com (HELO email-inbound-relay-2a-e7be2041.us-west-2.amazon.com) ([10.124.125.6]) by smtp-border-fw-out-6001.iad6.amazon.com with ESMTP/TLS/DHE-RSA-AES256-SHA; 07 Sep 2018 21:41:22 +0000 Received: from u7588a65da6b65f.ant.amazon.com (pdx2-ws-svc-lb17-vlan3.amazon.com [10.247.140.70]) by email-inbound-relay-2a-e7be2041.us-west-2.amazon.com (8.14.7/8.14.7) with ESMTP id w87LfHmi096499 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=FAIL); Fri, 7 Sep 2018 21:41:19 GMT Received: from u7588a65da6b65f.ant.amazon.com (localhost [127.0.0.1]) by u7588a65da6b65f.ant.amazon.com (8.15.2/8.15.2/Debian-3) with ESMTPS id w87LfFsG027125 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Fri, 7 Sep 2018 23:41:15 +0200 Received: (from jschoenh@localhost) by u7588a65da6b65f.ant.amazon.com (8.15.2/8.15.2/Submit) id w87LfEYn027124; Fri, 7 Sep 2018 23:41:14 +0200 From: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= To: Ingo Molnar , Peter Zijlstra Cc: =?UTF-8?q?Jan=20H=2E=20Sch=C3=B6nherr?= , linux-kernel@vger.kernel.org Subject: [RFC 04/60] sched: Replace sd_numa_mask() hack with something sane Date: Fri, 7 Sep 2018 23:39:51 +0200 Message-Id: <20180907214047.26914-5-jschoenh@amazon.de> X-Mailer: git-send-email 2.9.3.1.gcba166c.dirty In-Reply-To: <20180907214047.26914-1-jschoenh@amazon.de> References: <20180907214047.26914-1-jschoenh@amazon.de> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Get rid of the global variable sched_domains_curr_level, which is used to pass state into a sd_numa_mask(), which is used as a callback for sched_domain_topology_level->mask(). Extend the ->mask() callback instead, so that it takes the topology level as an extra argument. Provide a backward compatible ->simple_mask() callback, so that existing code can stay as it is. This enables other users to do queries via ->mask() without having to worry about the global variable. It also opens up the possibility for more generic topologies that require a dynamic number of levels (similar to what NUMA already does on top of the system topology). Signed-off-by: Jan H. Schönherr --- include/linux/sched/topology.h | 11 ++++++++--- kernel/sched/topology.c | 40 ++++++++++++++++++++++------------------ 2 files changed, 30 insertions(+), 21 deletions(-) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 530ad856372e..f78534f1cc1e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -165,7 +165,11 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms); bool cpus_share_cache(int this_cpu, int that_cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); +struct sched_domain_topology_level; + +typedef const struct cpumask *(*sched_domain_simple_mask_f)(int cpu); +typedef const struct cpumask *(*sched_domain_mask_f)(struct sched_domain_topology_level *tl, + int cpu); typedef int (*sched_domain_flags_f)(void); #define SDTL_OVERLAP 0x01 @@ -178,10 +182,11 @@ struct sd_data { }; struct sched_domain_topology_level { - sched_domain_mask_f mask; + sched_domain_simple_mask_f simple_mask; sched_domain_flags_f sd_flags; + sched_domain_mask_f mask; int flags; - int numa_level; + int level; struct sd_data data; #ifdef CONFIG_SCHED_DEBUG char *name; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 8b64f3f57d50..0f2c3aa0a097 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1043,7 +1043,6 @@ static void claim_allocations(int cpu, struct sched_domain *sd) enum numa_topology_type sched_numa_topology_type; static int sched_domains_numa_levels; -static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; @@ -1084,15 +1083,9 @@ sd_init(struct sched_domain_topology_level *tl, struct sd_data *sdd = &tl->data; struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); int sd_id, sd_weight, sd_flags = 0; + const struct cpumask *mask = tl->mask(tl, cpu); -#ifdef CONFIG_NUMA - /* - * Ugly hack to pass state to sd_numa_mask()... - */ - sched_domains_curr_level = tl->numa_level; -#endif - - sd_weight = cpumask_weight(tl->mask(cpu)); + sd_weight = cpumask_weight(mask); if (tl->sd_flags) sd_flags = (*tl->sd_flags)(); @@ -1138,7 +1131,7 @@ sd_init(struct sched_domain_topology_level *tl, #endif }; - cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + cpumask_and(sched_domain_span(sd), cpu_map, mask); sd_id = cpumask_first(sched_domain_span(sd)); /* @@ -1170,7 +1163,7 @@ sd_init(struct sched_domain_topology_level *tl, sd->idle_idx = 2; sd->flags |= SD_SERIALIZE; - if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + if (sched_domains_numa_distance[tl->level] > RECLAIM_DISTANCE) { sd->flags &= ~(SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE); @@ -1195,17 +1188,23 @@ sd_init(struct sched_domain_topology_level *tl, return sd; } +static const struct cpumask * +sd_simple_mask(struct sched_domain_topology_level *tl, int cpu) +{ + return tl->simple_mask(cpu); +} + /* * Topology list, bottom-up. */ static struct sched_domain_topology_level default_topology[] = { #ifdef CONFIG_SCHED_SMT - { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, + { cpu_smt_mask, cpu_smt_flags, sd_simple_mask, SD_INIT_NAME(SMT) }, #endif #ifdef CONFIG_SCHED_MC - { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_coregroup_mask, cpu_core_flags, sd_simple_mask, SD_INIT_NAME(MC) }, #endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { cpu_cpu_mask, NULL, sd_simple_mask, SD_INIT_NAME(DIE) }, { NULL, }, }; @@ -1221,13 +1220,18 @@ void set_sched_topology(struct sched_domain_topology_level *tl) return; sched_domain_topology = tl; + for (; tl->mask || tl->simple_mask; tl++) { + if (tl->simple_mask) + tl->mask = sd_simple_mask; + } } #ifdef CONFIG_NUMA -static const struct cpumask *sd_numa_mask(int cpu) +static const struct cpumask * +sd_numa_mask(struct sched_domain_topology_level *tl, int cpu) { - return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; + return sched_domains_numa_masks[tl->level][cpu_to_node(cpu)]; } static void sched_numa_warn(const char *str) @@ -1446,7 +1450,7 @@ void sched_init_numa(void) */ tl[i++] = (struct sched_domain_topology_level){ .mask = sd_numa_mask, - .numa_level = 0, + .level = 0, SD_INIT_NAME(NODE) }; @@ -1458,7 +1462,7 @@ void sched_init_numa(void) .mask = sd_numa_mask, .sd_flags = cpu_numa_flags, .flags = SDTL_OVERLAP, - .numa_level = j, + .level = j, SD_INIT_NAME(NUMA) }; } -- 2.9.3.1.gcba166c.dirty